检索结果-内蒙古大学图书馆

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Kiziltepe, Rukiye Savran Ezin, Ercan Karakus, Murat Dept. of Software Engineering Karadeniz Tech. University Trabzon Turkey Dept. of Computer Engineering Harran University Şanlıurfa Turkey Dept. of Software Engineering Ankara University Ankara Turkey

ISBN: (纸本)9798350379433

This study investigates the performance of traditional Machine Learning (ML) models for Sentiment Analysis (SA) in the Turkish language, addressing the growing need for robust Natural Language Processing (NLP) techniques in low-resource languages. We compare the efficacy of Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Naive Bayes (NB) classifiers on two recently developed large-scale Turkish sentiment datasets: "Vitamins and Supplements Customer Review" (VSCR) and "Turkish Sentiment Analysis version 1" (TRSAv1). Our research leverages advanced hyperparameter tuning techniques to optimize these models, providing benchmarks and practical insights for Turkish SA. The study contributes to the field by establishing performance baselines on new open-source datasets, enhancing understanding of NLP models for agglutinative languages, and analyzing factors affecting classifier performance in binary and multi-class scenarios. Our findings reveal the strengths and limitations of each model within the context of Turkish language SA, offering valuable guidance for future research and applications in this domain. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Rapid Thermal Modeling and Discharge Characterization for Accurate Lithium-ion Battery Core Temperature Estimation 48

Rapid Thermal Modeling and Discharge Characterization for Ac...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Samanta, Akash Huynh, Alvin Rutovic, Emmanuel Williamson, Sheldon Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada AESIM. Tech Montreal Canada

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

The increasing events of fire and catastrophic failure of lithium-ion batteries (LIBs) due to inaccurate thermal information or improper thermal management based on surface temperature data only, once again indicates the necessity of accurate core temperature information. In view of this, a rapid, more convenient but accurate thermal modeling technique for LIB is introduced in this paper using SIMBA. SIMBA is a powerful new generation power electronics simulation software powered by Python. A second-order electro-thermal model-based core temperature estimation scheme is developed in SIMBA. A wide range of battery test data is used for experimental validation of the model. Further, four standard drive cycle profiles are used to assess the impact of discharge current on the core temperature of LIB. The electro-thermal model allows estimating the core temperature from external measurements including voltage, current, and surface temperature without installing a physical core temperature sensor which is practically challenging. The proposed modeling technique is extremely convenient and the model is computationally efficient and simple enough to be implemented in practical purpose lithium-ion battery management systems. © 2022 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

FaultLLAMA2: A Fine Tuned Large Language Model for Code Recommendations to Reduce Java Lock Contention 34

FaultLLAMA2: A Fine Tuned Large Language Model for Code Reco...

引用

34th Annual International Conference on Collaborative Advances in software and Computing, CASCON 2024

作者： Shawon, Ashadullah Liscano, Ramiro Azim, Akramul Sundaresan, Vijay Chang, Yee-Kang Ontario Tech University Electrical and Computer Engineering Oshawa Canada IBM IBM Toronto Lab Toronto Canada

ISBN: (纸本)9798331504830

Lock contention occurs when multiple threads or processes try to access the same lock simultaneously, often causing performance degradation in software that runs concurrent threads. In this paper, we propose a new recommendation model that leverages Large Language Models (LLMs) and suggests refactored source code to alleviate lock contention faults. Our proposed FaultLLAMA2 model is based on a fine-tuned customization of the generalized LLAMA2 LLM model. FaultLLAMA2 is fine-tuned on examples of lock contention anti-patterns and their associated recommendations. Our results show that the accuracy of the FaultLLAMA2 model was on average 2.7 times higher than the LLAMA2 baseline model based on the BLED and Pass@K metrics. We also compared the FaultLLAMA2 model recommendations with a CodeBERT code generation model fine-tuned for lock contention recommendations and its accuracy was 4 times better. © 2024 IEEE.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

A Solid State Transformer-based Charging Station for Catering Heavy/Medium and Light Electric Vehicles

A Solid State Transformer-based Charging Station for Caterin...

引用

Workshop on Smart Grid and Renewable Energy (SGRE)

作者： Ruvini De Seram Kushan Tharuka Lulbadda Tarlochan Sidhu Sheldon S. Williamson Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

Incorporating solid-state transformers into EV charging stations can greatly improve their power density, reliability, efficiency, etc. This paper presents an solid state transformer (SST)-based EV charging station that can cater to three different types of vehicles according to the charging power requirement; heavy, medium, and light electric vehicles. Also, the proposed charging station provides both AC on-board charging and DC off-board charging ports. A MATLAB model of the proposed system was developed and simulated to validate the feasibility. The simulation results verifies that the proposed 10 kV, 1 MVA charging station is capable of charging the all categories of electric vehicles from 20% state of charge (SoC) to 80% SoC within 17.8 mins using constant current charging strategy. Furthermore, one heavy duty electric vehicle which is 30% of the charging station capacity is disconnected to demonstrate a sudden EV demand drop and the total harmonic distortion (THD) of grid current is observed to be laid below 2.6% before and after the event of disconnecting ensuring the stability of the proposed system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Quad-Active Bridge (QAB)-Based Solid-State Transformer for Fast Charging of Light/Medium and Heavy Electric Vehicles

A Quad-Active Bridge (QAB)-Based Solid-State Transformer for...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Ruvini De Seram Kushan Tharuka Lulbadda Tarlochan Sidhu Sheldon S. Williamson Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

Integrating electric vehicle (EV) fast charging stations with the medium voltage (MV) grid using a solid-state transformer (SST) has attracted more interest from researchers due to the reduced size and the smart functionalities it offers for maintaining the stability and power quality of the grid. However, the modular structure of SST requires many power converters and high-frequency transformers in the isolated DC/DC converter stage which again increases the space of the charging station. This paper proposes a design of an SST-based EV charging station using a quadruple-active-bridge (QAB) as the isolated DC/DC converter and investigates the power density enhancement compared to the dual-active-bridge (DAB)–based system. The proposed charging station can charge different EVs with different battery voltages (800V, 400V, and 200V) and capacities. The performance is validated by simulating a 1MVA, 10kV EV charging station using MATLAB. The control architecture and a detailed analysis of the system are included in the paper.

关键词： Power system measurements Density measurement Bridge circuits Space charge Electric vehicle charging Stability analysis Batteries

来源：评论

学校读者我要写书评

暂无评论

Uncertainty measurement for complex event prediction in safety-critical systems

arXiv

引用

arXiv 2024年

作者： Peixoto, Maria J.P. Azim, Akramul Department of Electrical Computer and Software Engineering Ontario Tech University OshawaON Canada

Complex events originate from other primitive events combined according to defined patterns and rules. Instead of using specialists’ manual work to compose the model rules, we use machine learning (ML) to self-define these patterns and regulations based on incoming input data to produce the desired complex event. Complex events processing (CEP) uncertainty is critical for embedded and safety-critical systems. This paper exemplifies how we can measure uncertainty for the perception and prediction of events, encompassing embedded systems that can also be critical to safety. Then, we propose an approach (ML CP) incorporating ML and sensitivity analysis that verifies how the output varies according to each input parameter. Furthermore, our model also measures the uncertainty associated with the predicted complex event. Therefore, we use conformal prediction to build prediction intervals, as the model itself has uncertainties, and the data has noise. Also, we tested our approach with classification (binary and multi-level) and regression problems test cases. Finally, we present and discuss our results, which are very promising within our field of research and work. © 2024, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Replay-Based Continual Learning for Test Case Prioritization

Replay-Based Continual Learning for Test Case Prioritization

引用

IEEE International Conference on software Testing Verification and Validation Workshop, ICSTW

作者： Asma Fariha Akramul Azim Ramiro Liscano Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

ISBN: (数字)9798350344790

ISBN: (纸本)9798350344806

In a large-scale Continuous Integration (CI) environment, regression testing can encounter high time and resource demands in ad hoc execution. Therefore, Test Case Prioritization (TCP) is crucial for enhancing the regression testing efficiency of CI. TCP methods aim to optimize regression testing by ordering test cases to effectively cover new code changes and their potential side effects and to maximize early fault detection. Traditional prioritization processes use diverse data sources, including code coverage analysis, test execution history, and domain-specific features. Heuristic-based or code-coverage-driven prioritization techniques may not be sufficient for accurate results in a rapidly changing environment. For this reason, there has been a significant shift towards employing Machine Learning (ML) techniques in TCP in recent years to harness the vast and complex datasets generated by CI practices. ML-based TCP approaches integrate multifaceted test case features from various sources to enhance the accuracy of test case prioritization. This trend reflects a broader movement towards data-driven decisionmaking in software testing, offering the potential to significantly reduce the regression testing burden by tailoring test suites more effectively to the needs of each software build, thereby saving time and resources while maintaining or improving the software quality. Recent studies have shown that the ML-based methods used in TCP can be categorized into four groups: Supervised Learning, Unsupervised Learning, Reinforcement Learning, and Natural Language Processing. Codebases for software projects can be changed rapidly by introducing new feature distributions into the CI systems. We analyzed a Java application’s CI and version control system (VCS) history data received from the International Business Machines Corporation (IBM) [1], [6], [7]. The frequent inclusion of new test suites introduced new patterns into the dataset properties. To keep up with these c

关键词： Continuing education Training software testing Time-frequency analysis Accuracy Codes Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Six Leads Are All You Need for Efficient Cardiac Analysis

Six Leads Are All You Need for Efficient Cardiac Analysis

引用

2023 IEEE Global Conference on Artificial Intelligence and Internet of Things, GCAIoT 2023

作者： Mousa, Ahmad Elgazzar, Khalid Ontario Tech University IoT Research Laboratory Electrical Computer and Software Engineering OshawaL1G 0C5 Canada

ISBN: (纸本)9798350382020

Electrocardiography (ECG) serves as a noninvasive method of monitoring the electrical activity of the heart by employing electrodes attached to the skin. These electrodes detect the minuscule electrical signals generated by the heart's activity. A conventional ECG, known as a 12-lead ECG, necessitates the positioning of 12 electrodes across the body to yield a detailed perspective of the heart's electrical function. Our study introduces an innovative approach to real-time ECG signal classification, using a maximum of six leads, with the aim of reducing the time and resources dedicated to data acquisition and signal processing without compromising accuracy. We introduce a technique for grouping leads and assess the performance of the classification of ECG signals on various leads. Our findings indicate that implementing lead-wise grouping with up to six leads results in a 93.67% reduction in sampling time, a 50% decrease in data size on the acquisition device, and an 84.72% cut in signal processing time, all while experiencing a minimal accuracy decrease of 0.08%. The efficacy of the proposed lead grouping has been assessed through the Kafka real-time platform. © 2023 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Comparative Analysis of Circular, Rectangular, and Hexagonal Coils for Wireless Charging of E-mobility

Comprehensive Comparative Analysis of Circular, Rectangular,...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Jeonggi Son Niranjan Shrestha Sheldon Williamson Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

The coil configuration is a critical element in wireless charging systems for electric vehicles (EVs). This paper presents a thorough comparison of commonly used circular, rectangular, and hexagonal coils for WPT application, specifically analyzing, reviewing, and evaluating their major electrical and physical properties. This paper includes two revised analytical models (optimized and non-optimized), Finite Element Analysis (FEA) analysis conducted on Ansys Maxwell, MATLAB Simulink results, and their experimental validation for all the coil mentioned above shapes to comprehensively compare some of their important parameters that impact the WPT system performance such as self-inductance, EMI performance, resistance, quality factor, volume, power transfer efficiency, weight, and cost. All the simulations are carried out for level 1 WPT (3.7 kW) whereas the experimental validation is performed for 2 kW.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protection Schemes of Solid State Transformers for Different Fault Conditions

Protection Schemes of Solid State Transformers for Different...

引用

Workshop on Smart Grid and Renewable Energy (SGRE)

作者： Kushan Tharuka Lulbadda Ruvini De Seram Tarlochan Sidhu Sheldon S. Williamson Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

The idea of a Solid-State Transformer (SST) has received much interest recently and is being thoroughly explored for use in the electrical system by replacing the traditional low-frequency transformer (LFT) using high-frequency isolated ACAC conversion. The SSTs are able to offer several additional functions than the traditional LFT. As the SST concept becomes popular among the power system, the safety of the system becomes vulnerable. The SST is made of a collection of several power electronic switches which has less reliability in general. Several kinds of faults can be caused by this issue like overcurrent, overvoltage, and overtemperature. These main issues are generally discussed in this paper to give a better idea of the faults that can happen in the system due to the integration of SSTs. In order to protect the SST a specific protection scheme must be needed. Further, it must have the ability to protect the system from disturbances coursed by the integration of SST. There are several protection schemes are available in the literature for the purpose of protecting the SST. Most of them are designed based on traditional power systems which are equipped with the LFTs. A few of them are discussed in this paper with their schematic diagrams to give a better understanding. The main focus of these protection systems is the protection of power electronic switches which will discussed in detail in this paper. Therefore, this paper will be a huge benefit for the researchers who are working on designing the protection systems for SST. Further, this paper will highlight the research areas that need more focus from a protection perspective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：